© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 154715
    Prev
    Next
    INDEX
    Explanations

    reading, eating, structure, knowledge, books

    np_acts-logits-general · gemini-2.5-flash-lite

    file path separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    нет
    0.54
    民主
    0.46
     в
    0.46
    ારી
    0.46
     Treasurer
    0.46
    чително
    0.46
    衊
    0.46
     tópico
    0.45
    、
    0.45
    рик
    0.44
    POSITIVE LOGITS
    zm
    0.52
    گا
    0.49
    navi
    0.46
    Api
    0.46
     polypeptides
    0.46
    labelled
    0.46
     postérieures
    0.45
    arguments
    0.45
    lympi
    0.44
    zg
    0.44
    Activations Density 0.000%

    No Known Activations